def test(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
gen = properties.PropertiesGenerator(kb, options={
'mean_doubling_time': 3600,
})
gen.run()
self.assertEqual(cell.properties.get_one(id='mean_doubling_time').value, 3600)
def test_generator(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
cell.taxon = 9606
cell.parameters.create(id='cell_volume', value=1E-15)
cell.parameters.create(id='mean_doubling_time',
value=20.,
units=unit_registry.parse_units('hour'))
compartments = {'c': 0.7, 'n': 0.3, 'e': None}
for k, v in compartments.items():
cell.compartments.create(id=k, volumetric_fraction=v)
test_component_generators = [initialize_model.InitializeModel]
gen = core.EukaryoteModelGenerator(
kb,
component_generators=test_component_generators,
options={
'id': 'h1_test',
'name': 'h1 model',
'version': '2.3.1',
'component': {
'InitializeModel': {
'cell_density': 1100.,
'gen_dna': False,
'gen_pre_rnas': False,
'gen_transcripts': False,
'gen_protein': False,
'gen_metabolites': False,
'gen_complexes': False,
'gen_distribution_init_concentrations': False,
'gen_observables': False,
'gen_kb_reactions': False,
'gen_kb_rate_laws': False,
}
}
})
model = gen.run()
self.assertEqual(model.id, 'h1_test')
self.assertEqual(model.name, 'h1 model')
self.assertEqual(model.version, '2.3.1')
self.assertEqual(
model.parameters.get_one(id='mean_doubling_time').value, 72000)
self.assertEqual(model.parameters.get_one(id='density_n').value, 1100)
self.assertEqual(model.parameters.get_one(id='density_e').value, 1000)
self.assertEqual(
model.compartments.get_one(id='n').init_volume.mean,
2.997832792664565e-16)
self.assertEqual(
model.compartments.get_one(id='e').init_volume.mean, 1.0)
def test_default(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
gen = compartments.CompartmentsGenerator(kb)
gen.run()
cytosol = cell.compartments.get_one(id='c')
self.assertEqual(cytosol.name, 'cytosol')
extra = cell.compartments.get_one(id='e')
self.assertEqual(extra.name, 'extracellular space')
def test_run(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
mean_num_genes = 200
gen = chrs_genes_tus.ChromosomesGenesTusGenerator(
kb,
options={
'num_chromosomes': 2,
'mean_gc_frac': 1,
'mean_num_genes': mean_num_genes,
'mean_gene_len': 100,
'mean_coding_frac': 0.75,
})
gen.run()
self.assertEqual(len(cell.species_types), 2)
gc = 0
chr_len = 0
for chr in cell.species_types:
gc += chr.seq.count('C') + chr.seq.count('G')
chr_len += len(chr.seq)
self.assertEqual(gc / chr_len, 1)
tus = cell.loci.get(__type=wc_kb.prokaryote.TranscriptionUnitLocus)
genes = cell.loci.get(__type=wc_kb.prokaryote.GeneLocus)
self.assertAlmostEqual(len(tus),
mean_num_genes,
delta=5 * numpy.sqrt(mean_num_genes))
self.assertAlmostEqual(len(genes),
mean_num_genes,
delta=5 * numpy.sqrt(mean_num_genes))
mu = 100 / 0.75 * 0.25 / 2
self.assertAlmostEqual(genes[0].start, mu, delta=5 * numpy.sqrt(mu))
gene_len = 0
gene_pos = 0
for gene in genes:
gene_len += gene.get_len()
gene_pos += gene.strand == wc_kb.core.PolymerStrand.positive
self.assertAlmostEqual(gene_len / len(genes),
100,
delta=5 * numpy.sqrt(100 / 100))
self.assertAlmostEqual(gene_pos / len(genes),
0.5,
delta=5 * numpy.sqrt((1 - 0.5) * 0.5 / 100))
self.assertAlmostEqual(gene_len / chr_len,
0.75,
delta=5 * numpy.sqrt((1 - 0.75) * 0.75 / 100))
def test(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
cell.properties.create(id='mean_volume',
value=1,
units=unit_registry.parse_units('L'))
cytosol = cell.compartments.get_one(id='c')
tus = []
for i_tu in range(1000):
tu = cell.loci.create(
__type=wc_kb.prokaryote.TranscriptionUnitLocus,
id='tu_{}'.format(i_tu + 1),
name='Transcription unit {}'.format(i_tu + 1),
start=10 + 20 * (i_tu),
end=20 + 20 * (i_tu),
strand=wc_kb.core.PolymerStrand.positive)
tu.genes.create(id='gene_{}'.format(i_tu + 1),
type=wc_kb.core.GeneType.mRna)
tus.append(tu)
gen = kb_gen.rna.RnaGenerator(kb,
options={
'mean_copy_number': 10.,
'mean_half_life': 120.,
})
gen.run()
rnas = cell.species_types.get(__type=wc_kb.prokaryote.RnaSpeciesType)
self.assertEqual(len(rnas), 1000)
self.assertEqual(rnas[0].transcription_units, [tus[0]])
self.assertEqual(rnas[0].name, 'RNA 1')
self.assertEqual(rnas[0].type, wc_kb.core.RnaType.mRna)
concs = [
rna.species.get_one(compartment=cytosol).concentration.value
for rna in rnas
]
half_lives = [rna.half_life for rna in rnas]
self.assertAlmostEqual(numpy.mean(concs),
10. / scipy.constants.Avogadro / 1.,
delta=5. * numpy.sqrt(10. / 1000.))
self.assertAlmostEqual(numpy.mean(half_lives),
120.,
delta=5. * numpy.sqrt(120. / 1000.))
def test_run(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
gen = compartments.CompartmentsGenerator(kb,
options={
'compartments':
[('c', 'cytosol'),
('e',
'extracellular space'),
('t', 'test')]
})
gen.run()
cytosol = cell.compartments.get_one(id='c')
self.assertEqual(cytosol.name, 'cytosol')
extra = cell.compartments.get_one(id='e')
self.assertEqual(extra.name, 'extracellular space')
test = cell.compartments.get_one(id='t')
self.assertEqual(test.name, 'test')
def test_validate_exception(self):
kb = wc_kb.KnowledgeBase(id='kb',
name='KB',
version='0.0.1a',
wc_kb_version='0.0.1')
kb.cell = wc_kb.Cell(id='cell')
kb.cell.compartments.create(id='c')
kb.cell.compartments.create(id='c')
self.assertNotEqual(Validator().run(kb, get_related=True), None)
filename_core = path.join(self.tempdir, 'core.xlsx')
filename_seq = path.join(self.tempdir, 'seq.fna')
io.Writer().run(kb,
filename_core,
filename_seq,
set_repo_metadata_from_path=False)
with self.assertRaisesRegex(SystemExit,
'^Knowledge base is invalid: '):
with __main__.App(
argv=['validate', filename_core, filename_seq]) as app:
app.run()
def test_run(self):
kb = wc_kb.KnowledgeBase()
cell = kb.cell = wc_kb.Cell()
gen = metabolites.MetabolitesGenerator(kb,
options={
'data_path': self.data_path,
})
gen.run()
h2o = cell.species_types.get_one(
__type=wc_kb.core.MetaboliteSpeciesType, id='h2o')
self.assertEqual(h2o.get_empirical_formula(),
wc_utils.util.chem.EmpiricalFormula('H2O'))
self.assertEqual(h2o.get_charge(), 0)
concs = cell.concentrations.get(__type=wc_kb.core.Concentration,
value=55.)
self.assertEqual(len(concs), 2)
c = cell.compartments.get_one(id='c')
e = cell.compartments.get_one(id='e')
h2o_c = h2o.species.get_one(compartment=c)
h2o_e = h2o.species.get_one(compartment=e)
self.assertEqual(set([conc.species for conc in concs]),
set([h2o_c, h2o_e]))
h = cell.species_types.get_one(__type=wc_kb.core.MetaboliteSpeciesType,
id='h')
self.assertEqual(h.get_empirical_formula(),
wc_utils.util.chem.EmpiricalFormula('H'))
self.assertEqual(h.get_charge(), 1)
self.assertEqual(
cell.concentrations.get_one(__type=wc_kb.core.Concentration,
value=1e-6).species.species_type, h)
self.assertEqual(
cell.concentrations.get_one(__type=wc_kb.core.Concentration,
value=1e-6).species.compartment, c)
def setUp(self):
# Create KB content
self.tmp_dirname = tempfile.mkdtemp()
self.sequence_path = os.path.join(self.tmp_dirname, 'test_seq.fasta')
with open(self.sequence_path, 'w') as f:
f.write('>chr1\nGCGTGCGATGAT\n'
'>chrM\nNGCGTGCGATGAT\n'
'>chrX\nATGtgaGCGtgatga\n')
self.kb = wc_kb.KnowledgeBase()
cell = self.kb.cell = wc_kb.Cell()
chr1 = wc_kb.core.DnaSpeciesType(cell=cell,
id='chr1',
sequence_path=self.sequence_path)
gene1 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene1',
polymer=chr1,
start=1,
end=12)
chrM = wc_kb.core.DnaSpeciesType(cell=cell,
id='chrM',
sequence_path=self.sequence_path)
geneM = wc_kb.eukaryote.GeneLocus(cell=cell,
id='geneM',
polymer=chrM,
start=2,
end=13)
chrX = wc_kb.core.DnaSpeciesType(cell=cell,
id='chrX',
sequence_path=self.sequence_path)
geneX1 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='geneX1',
polymer=chrX,
start=1,
end=15)
geneX2 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='geneX2',
polymer=chrX,
start=1,
end=15)
locus1 = wc_kb.eukaryote.GenericLocus(start=1, end=6)
transcript1 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
gene=gene1,
exons=[locus1])
prot1 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='prot1',
name='protein1',
transcript=transcript1,
coding_regions=[locus1])
prot1_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=prot1,
value='40000.0',
value_type=wc_ontology['WC:float'])
locus2 = wc_kb.eukaryote.GenericLocus(start=4, end=9)
transcript2 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
gene=gene1,
exons=[locus2])
prot2 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='prot2',
name='protein2',
transcript=transcript2,
coding_regions=[locus2])
prot2_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=prot2,
value='40000.0',
value_type=wc_ontology['WC:float'])
locus3 = wc_kb.eukaryote.GenericLocus(start=7, end=12)
transcript3 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
gene=gene1,
exons=[locus3])
prot3 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='prot3',
name='protein3',
transcript=transcript3,
coding_regions=[locus3])
prot3_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=prot3,
value='25000.0',
value_type=wc_ontology['WC:float'])
locusM = wc_kb.eukaryote.GenericLocus(start=8, end=13)
transcriptM = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
gene=geneM,
exons=[locusM])
protM = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='protM',
name='proteinM',
transcript=transcriptM,
coding_regions=[locusM])
protM_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=protM,
value='25000.0',
value_type=wc_ontology['WC:float'])
locusX1 = wc_kb.eukaryote.GenericLocus(start=1, end=15)
transcriptX1 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
gene=geneX1,
exons=[locusX1])
protX1 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='protX1',
name='proteinX1',
transcript=transcriptX1,
coding_regions=[locusX1])
protX1_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=protX1,
value='25000.0',
value_type=wc_ontology['WC:float'])
locusX2 = wc_kb.eukaryote.GenericLocus(start=1, end=15)
transcriptX2 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
gene=geneX2,
exons=[locusX2])
protX2 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='protX2',
name='proteinX2',
transcript=transcriptX2,
coding_regions=[locusX2])
protX2_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=protX2,
value='25000.0',
value_type=wc_ontology['WC:float'])
# Create initial model content
self.model = model = wc_lang.Model()
model.parameters.create(
id='Avogadro',
value=scipy.constants.Avogadro,
units=unit_registry.parse_units('molecule mol^-1'))
compartments = {
'n': ('nucleus', 5E-14),
'c': ('cytoplasm', 1E-13),
'm': ('mitochondria', 2.5E-14),
'l': ('lysosome', 1.5E-14),
'c_m': ('membrane', 5E-15)
}
for k, v in compartments.items():
init_volume = wc_lang.core.InitVolume(
distribution=wc_ontology['WC:normal_distribution'],
mean=v[1],
std=0)
c = model.compartments.create(id=k,
name=v[0],
init_volume=init_volume)
c.init_density = model.parameters.create(
id='density_' + k,
value=1000,
units=unit_registry.parse_units('g l^-1'))
volume = model.functions.create(
id='volume_' + k, units=unit_registry.parse_units('l'))
volume.expression, error = wc_lang.FunctionExpression.deserialize(
f'{c.id} / {c.init_density.id}', {
wc_lang.Compartment: {
c.id: c
},
wc_lang.Parameter: {
c.init_density.id: c.init_density
},
})
assert error is None, str(error)
proteins = {
'prot1': ['n', 'c'],
'prot2': ['c', 'l'],
'prot3': ['l'],
'protM': ['m', 'c_m'],
'protX1': ['l'],
'protX2': ['l']
}
for k, v in proteins.items():
kb_protein = cell.species_types.get_one(id=k)
model_species_type = model.species_types.create(
id=kb_protein.id,
name=kb_protein.name,
type=wc_ontology['WC:protein'])
for comp in v:
model_compartment = model.compartments.get_one(id=comp)
model_species = model.species.create(
species_type=model_species_type,
compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=10,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
model.distribution_init_concentrations.get_one(
id='dist-init-conc-protM[m]').mean = 0.
complexes = {
'comp_1': ('26S proteasome', ['n', 'c']),
'comp_2': ('lonp1', ['m']),
'comp_3': ('clpp', ['m']),
'comp_4': ('cathepsin B', ['l']),
'comp_5': ('cathepsin D', ['l'])
}
for k, v in complexes.items():
model_species_type = model.species_types.create(
id=k, name=v[0], type=wc_ontology['WC:pseudo_species'])
for comp in v[1]:
model_compartment = model.compartments.get_one(id=comp)
model_species = model.species.create(
species_type=model_species_type,
compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=2,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
metabolic_participants = [
'Ala', 'Cys', 'Asp', 'Glu', 'Met', 'Selcys', 'h2o'
]
metabolic_compartments = ['l', 'm']
for i in metabolic_participants:
for c in metabolic_compartments:
model_species_type = model.species_types.get_or_create(
id=i, type=wc_ontology['WC:metabolite'])
model_compartment = model.compartments.get_one(id=c)
model_species = model.species.get_or_create(
species_type=model_species_type,
compartment=model_compartment)
model_species.id = model_species.gen_id()
def setUp(self):
# Create KB content
self.tmp_dirname = tempfile.mkdtemp()
self.sequence_path = os.path.join(self.tmp_dirname, 'test_seq.fasta')
with open(self.sequence_path, 'w') as f:
f.write('>chr1\nTTTATGACTCTAGTTTAT\n'
'>chrM\nTTTatgaCTCTAGTTTAT\n')
self.kb = wc_kb.KnowledgeBase()
cell = self.kb.cell = wc_kb.Cell()
nucleus = cell.compartments.create(id='n')
mito = cell.compartments.create(id='m')
cytoplasm = cell.compartments.create(id='c')
chr1 = wc_kb.core.DnaSpeciesType(cell=cell,
id='chr1',
sequence_path=self.sequence_path)
gene1 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene1',
polymer=chr1,
start=1,
end=18)
exon1 = wc_kb.eukaryote.GenericLocus(start=4, end=18)
transcript1 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans1',
name='transcript1',
gene=gene1,
exons=[exon1])
transcript1_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript1,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript1_spec = wc_kb.core.Species(species_type=transcript1,
compartment=cytoplasm)
transcript1_conc = wc_kb.core.Concentration(cell=cell,
species=transcript1_spec,
value=10.)
chrM = wc_kb.core.DnaSpeciesType(cell=cell,
id='chrM',
sequence_path=self.sequence_path)
gene2 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene2',
polymer=chrM,
start=1,
end=18)
exon2 = wc_kb.eukaryote.GenericLocus(start=1, end=10)
transcript2 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans2',
name='transcript2',
gene=gene2,
exons=[exon2])
transcript2_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript2,
value='15000.0',
value_type=wc_ontology['WC:float'])
transcript2_spec = wc_kb.core.Species(species_type=transcript2,
compartment=mito)
transcript2_conc = wc_kb.core.Concentration(cell=cell,
species=transcript2_spec,
value=10.)
transcript3 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans3',
name='transcript3',
gene=gene2,
exons=[exon2])
transcript3_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript3,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript3_spec = wc_kb.core.Species(species_type=transcript3,
compartment=mito)
transcript3_conc = wc_kb.core.Concentration(cell=cell,
species=transcript3_spec,
value=10.)
transcript4 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans4',
name='transcript4',
gene=gene2,
exons=[exon2])
transcript4_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript4,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript4_spec = wc_kb.core.Species(species_type=transcript4,
compartment=mito)
transcript4_conc = wc_kb.core.Concentration(cell=cell,
species=transcript4_spec,
value=0.)
transcript5 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans5',
name='transcript5',
gene=gene2)
transcript5_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript5,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript5_spec = wc_kb.core.Species(species_type=transcript5,
compartment=mito)
transcript5_conc = wc_kb.core.Concentration(cell=cell,
species=transcript5_spec,
value=0.)
# Create initial model content
self.model = model = wc_lang.Model()
model.parameters.create(
id='Avogadro',
value=scipy.constants.Avogadro,
units=unit_registry.parse_units('molecule mol^-1'))
compartments = {
'n': ('nucleus', 5E-14),
'm': ('mitochondria', 2.5E-14),
'c': ('cytoplasm', 9E-14)
}
for k, v in compartments.items():
init_volume = wc_lang.core.InitVolume(
distribution=wc_ontology['WC:normal_distribution'],
mean=v[1],
std=0)
c = model.compartments.create(id=k,
name=v[0],
init_volume=init_volume)
c.init_density = model.parameters.create(
id='density_' + k,
value=1000,
units=unit_registry.parse_units('g l^-1'))
volume = model.functions.create(
id='volume_' + k, units=unit_registry.parse_units('l'))
volume.expression, error = wc_lang.FunctionExpression.deserialize(
f'{c.id} / {c.init_density.id}', {
wc_lang.Compartment: {
c.id: c
},
wc_lang.Parameter: {
c.init_density.id: c.init_density
},
})
assert error is None, str(error)
for i in cell.species_types.get(
__type=wc_kb.eukaryote.TranscriptSpeciesType):
model_species_type = model.species_types.create(id=i.id,
name=i.name)
model_compartment = model.compartments.get_one(
id='m' if 'M' in i.gene.polymer.id else 'c')
model_species = model.species.get_or_create(
species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=10.,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
model.distribution_init_concentrations.get_one(
id='dist-init-conc-trans4[m]').mean = 0.
ribo_site_species_type = model.species_types.create(
id='trans2_ribosome_binding_site')
mitochondria = model.compartments.get_one(id='m')
ribo_site_species = model.species.create(
species_type=ribo_site_species_type, compartment=mitochondria)
ribo_site_species.id = ribo_site_species.gen_id()
conc_ribo_site_species = model.distribution_init_concentrations.create(
species=ribo_site_species,
mean=20,
units=unit_registry.parse_units('molecule'))
conc_ribo_site_species.id = conc_ribo_site_species.gen_id()
complexes = {
'complex1': ('Exosome', ['c', 'n']),
'complex2': ('Exosome variant', ['c', 'n']),
'complex3': ('Mitochondrial Exosome', ['m']),
'complex4': ('Mitochondrial Exosome variant', ['m'])
}
for k, v in complexes.items():
model_species_type = model.species_types.get_or_create(id=k,
name=v[0])
for comp in v[1]:
model_compartment = model.compartments.get_one(id=comp)
model_species = model.species.get_or_create(
species_type=model_species_type,
compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=100.,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
metabolic_participants = ['amp', 'cmp', 'gmp', 'ump', 'h2o', 'h']
for i in metabolic_participants:
model_species_type = model.species_types.create(id=i)
for c in ['n', 'm', 'c']:
model_compartment = model.compartments.get_one(id=c)
model_species = model.species.get_or_create(
species_type=model_species_type,
compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=1500.,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
def setUp(self):
# Create KB content
self.tmp_dirname = tempfile.mkdtemp()
self.sequence_path = os.path.join(self.tmp_dirname, 'test_seq.fasta')
with open(self.sequence_path, 'w') as f:
f.write('>chr1\nGCGTGCGATGATtgatga\n')
self.kb = wc_kb.KnowledgeBase()
cell = self.kb.cell = wc_kb.Cell()
nucleus = cell.compartments.create(id='n')
mito = cell.compartments.create(id='m')
lysosome = cell.compartments.create(id='l')
membrane = cell.compartments.create(id='c_m')
chr1 = wc_kb.core.DnaSpeciesType(cell=cell, id='chr1', sequence_path=self.sequence_path)
gene1 = wc_kb.eukaryote.GeneLocus(cell=cell, id='gene1', polymer=chr1, start=1, end=18)
locus1 = wc_kb.eukaryote.GenericLocus(start=1, end=6)
transcript1 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell, gene=gene1, exons=[locus1])
prot1 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell, id='prot1', name='protein1', transcript=transcript1, coding_regions=[locus1])
prot1_half_life = wc_kb.core.SpeciesTypeProperty(property='half-life', species_type=prot1,
value='40000.0', value_type=wc_ontology['WC:float'])
prot1_spec = wc_kb.core.Species(species_type=prot1, compartment=nucleus)
locus2 = wc_kb.eukaryote.GenericLocus(start=4, end=9)
transcript2 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell, gene=gene1, exons=[locus2])
prot2 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell, id='prot2', name='protein2', transcript=transcript2, coding_regions=[locus2])
prot2_half_life = wc_kb.core.SpeciesTypeProperty(property='half-life', species_type=prot2,
value='20000.0', value_type=wc_ontology['WC:float'])
prot2_spec = wc_kb.core.Species(species_type=prot2, compartment=nucleus)
locus3 = wc_kb.eukaryote.GenericLocus(start=7, end=12)
transcript3 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell, gene=gene1, exons=[locus3])
prot3 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell, id='prot3', name='protein3', transcript=transcript3, coding_regions=[locus3])
prot3_half_life = wc_kb.core.SpeciesTypeProperty(property='half-life', species_type=prot3,
value='25000.0', value_type=wc_ontology['WC:float'])
prot3_spec1 = wc_kb.core.Species(species_type=prot3, compartment=nucleus)
prot3_spec2 = wc_kb.core.Species(species_type=prot3, compartment=mito)
prot3_spec3 = wc_kb.core.Species(species_type=prot3, compartment=membrane)
locus4 = wc_kb.eukaryote.GenericLocus(start=10, end=18)
transcript4 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell, gene=gene1, exons=[locus4])
prot4 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell, id='prot4', name='protein4', transcript=transcript4, coding_regions=[locus4])
prot4_half_life = wc_kb.core.SpeciesTypeProperty(property='half-life', species_type=prot4,
value='40000.0', value_type=wc_ontology['WC:float'])
prot4_spec = wc_kb.core.Species(species_type=prot4, compartment=nucleus)
met1 = wc_kb.core.MetaboliteSpeciesType(cell=cell, id='met1', name='metabolite1')
for i in cell.compartments:
met1_species = wc_kb.core.Species(species_type=met1, compartment=i)
complex1 = wc_kb.core.ComplexSpeciesType(cell=cell, id='complex_1', subunits=[
wc_kb.core.SpeciesTypeCoefficient(species_type=prot1, coefficient=1),
wc_kb.core.SpeciesTypeCoefficient(species_type=prot2, coefficient=2),
wc_kb.core.SpeciesTypeCoefficient(species_type=prot3, coefficient=0),
])
complex2 = wc_kb.core.ComplexSpeciesType(cell=cell, id='complex_2', subunits=[
wc_kb.core.SpeciesTypeCoefficient(species_type=prot3, coefficient=2),
wc_kb.core.SpeciesTypeCoefficient(species_type=met1, coefficient=2),
])
complex3 = wc_kb.core.ComplexSpeciesType(cell=cell, id='complex_3', subunits=[
wc_kb.core.SpeciesTypeCoefficient(species_type=prot4, coefficient=2),
])
# Create initial model content
self.model = model = wc_lang.Model()
model.parameters.create(id='Avogadro', value = scipy.constants.Avogadro,
units = unit_registry.parse_units('molecule mol^-1'))
compartments = {'n': ('nucleus', 5E-14), 'm': ('mitochondria', 2.5E-14), 'l': ('lysosome', 2.5E-14), 'c_m': ('membrane', 5E-15)}
for k, v in compartments.items():
init_volume = wc_lang.core.InitVolume(distribution=wc_ontology['WC:normal_distribution'],
mean=v[1], std=0)
c = model.compartments.create(id=k, name=v[0], init_volume=init_volume)
c.init_density = model.parameters.create(id='density_' + k, value=1000,
units=unit_registry.parse_units('g l^-1'))
volume = model.functions.create(id='volume_' + k, units=unit_registry.parse_units('l'))
volume.expression, error = wc_lang.FunctionExpression.deserialize(f'{c.id} / {c.init_density.id}', {
wc_lang.Compartment: {c.id: c},
wc_lang.Parameter: {c.init_density.id: c.init_density},
})
assert error is None, str(error)
for i in cell.species_types.get(__type=wc_kb.eukaryote.ProteinSpeciesType):
model_species_type = model.species_types.get_or_create(id=i.id, name=i.name, type=wc_ontology['WC:protein'])
model_compartment = model.compartments.get_one(id='n')
model_species = model.species.get_or_create(species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.get_or_create(species=model_species,
mean=10, units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
model_species_type = model.species_types.get_or_create(id='prot3', name='protein3', type=wc_ontology['WC:protein'])
model_mito = model.compartments.get_one(id='m')
model_species = model.species.get_or_create(species_type=model_species_type, compartment=model_mito)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(species=model_species,
mean=20, units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
model_membrane = model.compartments.get_one(id='c_m')
model_species = model.species.get_or_create(species_type=model_species_type, compartment=model_membrane)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(species=model_species,
mean=20, units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
model_species_type = model.species_types.get_or_create(id='met1', name='metabolite1', type=wc_ontology['WC:metabolite'])
for compartment in model.compartments:
model_species = model.species.get_or_create(species_type=model_species_type, compartment=compartment)
model_species.id = model_species.gen_id()
for compl in [complex1, complex2, complex3]:
model_species_type = model.species_types.create(id=compl.id, type=wc_ontology['WC:pseudo_species'])
subunit_compartments = [[s.compartment.id for s in sub.species_type.species]
for sub in compl.subunits]
if len(subunit_compartments) == 1:
shared_compartments = set(subunit_compartments[0])
else:
shared_compartments = set([])
for i in range(len(subunit_compartments)):
shared_compartments = (set(subunit_compartments[i])
if i==0 else shared_compartments).intersection(
set(subunit_compartments[i+1]) if i<(len(subunit_compartments)-1) else shared_compartments)
compartment_ids = set(list(shared_compartments))
for compartment_id in compartment_ids:
model_compartment = model.compartments.get_one(id=compartment_id)
model_species = model.species.get_or_create(species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
metabolic_participants = ['Ala', 'Cys', 'Asp', 'Glu', 'Selcys', 'h2o']
metabolic_compartments = ['l', 'm']
for i in metabolic_participants:
for c in metabolic_compartments:
model_species_type = model.species_types.get_or_create(id=i, type=wc_ontology['WC:metabolite'])
model_compartment = model.compartments.get_one(id=c)
model_species = model.species.get_or_create(species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
def setUp(self):
# Create KB content
self.tmp_dirname = tempfile.mkdtemp()
self.sequence_path = os.path.join(self.tmp_dirname, 'test_seq.fasta')
with open(self.sequence_path, 'w') as f:
f.write('>chr1\nATGCATGACTCTAGTTTAT\n'
'>chrM\nTTTatgaCTCTAGTTTACNNN\n')
self.kb = wc_kb.KnowledgeBase()
cell = self.kb.cell = wc_kb.Cell()
nucleus = cell.compartments.create(id='n')
mito = cell.compartments.create(id='m')
cytoplasm = cell.compartments.create(id='c')
chr1 = wc_kb.core.DnaSpeciesType(cell=cell,
id='chr1',
sequence_path=self.sequence_path)
gene1 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene1',
polymer=chr1,
start=1,
end=19)
exon1 = wc_kb.eukaryote.GenericLocus(start=5, end=19)
transcript1 = wc_kb.eukaryote.TranscriptSpeciesType(
cell=cell,
id='trans1',
name='transcript1',
gene=gene1,
exons=[exon1],
type=wc_kb.eukaryote.TranscriptType.mRna)
transcript1_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript1,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript1_spec = wc_kb.core.Species(species_type=transcript1,
compartment=cytoplasm)
transcript1_conc = wc_kb.core.Concentration(cell=cell,
species=transcript1_spec,
value=10.)
chrM = wc_kb.core.DnaSpeciesType(cell=cell,
id='chrM',
sequence_path=self.sequence_path)
gene2 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene2',
polymer=chrM,
start=1,
end=19)
exon2 = wc_kb.eukaryote.GenericLocus(start=1, end=10)
transcript2 = wc_kb.eukaryote.TranscriptSpeciesType(
cell=cell,
id='trans2',
name='transcript2',
gene=gene2,
exons=[exon2],
type=wc_kb.eukaryote.TranscriptType.mRna)
transcript2_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript2,
value='15000.0',
value_type=wc_ontology['WC:float'])
transcript2_spec = wc_kb.core.Species(species_type=transcript2,
compartment=mito)
transcript2_conc = wc_kb.core.Concentration(cell=cell,
species=transcript2_spec,
value=10.)
gene3 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene3',
polymer=chr1,
start=1,
end=19)
exon3 = wc_kb.eukaryote.GenericLocus(start=1, end=15)
transcript3 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans3',
name='transcript3',
gene=gene3,
exons=[exon3])
transcript3_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript3,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript3_spec = wc_kb.core.Species(species_type=transcript3,
compartment=cytoplasm)
transcript3_conc = wc_kb.core.Concentration(cell=cell,
species=transcript3_spec,
value=10.)
gene4 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene4',
polymer=chr1,
start=1,
end=3)
exon4 = wc_kb.eukaryote.GenericLocus(start=1, end=3)
transcript4 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans4',
name='transcript4',
gene=gene4,
exons=[exon4])
transcript4_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript4,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript4_spec = wc_kb.core.Species(species_type=transcript4,
compartment=cytoplasm)
transcript4_conc = wc_kb.core.Concentration(cell=cell,
species=transcript4_spec,
value=10.)
gene5 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene5',
polymer=chr1,
start=1,
end=3)
exon5 = wc_kb.eukaryote.GenericLocus(start=1, end=3)
transcript5 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans5',
name='transcript5',
gene=gene5,
exons=[exon5])
transcript5_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript5,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript5_spec = wc_kb.core.Species(species_type=transcript5,
compartment=cytoplasm)
transcript5_conc = wc_kb.core.Concentration(cell=cell,
species=transcript5_spec,
value=0.)
gene6 = wc_kb.eukaryote.GeneLocus(cell=cell,
id='gene6',
polymer=chr1,
start=1,
end=3)
exon6 = wc_kb.eukaryote.GenericLocus(start=1, end=3)
transcript6 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans6',
name='transcript6',
gene=gene6,
exons=[exon6])
transcript6_half_life = wc_kb.core.SpeciesTypeProperty(
property='half-life',
species_type=transcript6,
value='36000.0',
value_type=wc_ontology['WC:float'])
transcript6_spec = wc_kb.core.Species(species_type=transcript6,
compartment=cytoplasm)
transcript6_conc = wc_kb.core.Concentration(cell=cell,
species=transcript6_spec,
value=0.)
transcript7 = wc_kb.eukaryote.TranscriptSpeciesType(
cell=cell,
id='trans7',
name='transcript7',
gene=gene6,
type=wc_kb.eukaryote.TranscriptType.mRna)
transcript7_spec = wc_kb.core.Species(species_type=transcript7,
compartment=cytoplasm)
transcript7_conc = wc_kb.core.Concentration(cell=cell,
species=transcript7_spec,
value=10.)
transcript8 = wc_kb.eukaryote.TranscriptSpeciesType(cell=cell,
id='trans8',
name='transcript8',
gene=gene6)
activator = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='activator')
repressor = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='repressor')
gene2_reg1 = gene2.regulatory_modules.create(
transcription_factor_regulation=[
wc_kb.eukaryote.TranscriptionFactorRegulation(
transcription_factor=activator,
direction=wc_kb.eukaryote.RegulatoryDirection.activation)
])
gene2_reg2 = gene2.regulatory_modules.create(
transcription_factor_regulation=[
wc_kb.eukaryote.TranscriptionFactorRegulation(
transcription_factor=repressor,
direction=wc_kb.eukaryote.RegulatoryDirection.repression)
])
activator2 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='activator2')
repressor2 = wc_kb.eukaryote.ProteinSpeciesType(cell=cell,
id='repressor2')
gene6_reg1 = gene6.regulatory_modules.create(
transcription_factor_regulation=[
wc_kb.eukaryote.TranscriptionFactorRegulation(
transcription_factor=activator2,
direction=wc_kb.eukaryote.RegulatoryDirection.activation)
])
gene6_reg2 = gene6.regulatory_modules.create(
transcription_factor_regulation=[
wc_kb.eukaryote.TranscriptionFactorRegulation(
transcription_factor=repressor2,
direction=wc_kb.eukaryote.RegulatoryDirection.repression)
])
# Create initial model content
self.model = model = wc_lang.Model()
model.parameters.create(id='mean_doubling_time',
value=20 * 3600,
units=unit_registry.parse_units('s'))
model.parameters.create(
id='Avogadro',
value=scipy.constants.Avogadro,
units=unit_registry.parse_units('molecule mol^-1'))
compartments = {
'n': ('nucleus', 5E-14),
'm': ('mitochondria', 2.5E-14),
'c': ('cytoplasm', 1E-13)
}
for k, v in compartments.items():
init_volume = wc_lang.core.InitVolume(
distribution=wc_ontology['WC:normal_distribution'],
mean=v[1],
std=0)
c = model.compartments.create(id=k,
name=v[0],
init_volume=init_volume)
c.init_density = model.parameters.create(
id='density_' + k,
value=1000,
units=unit_registry.parse_units('g l^-1'))
volume = model.functions.create(
id='volume_' + k, units=unit_registry.parse_units('l'))
volume.expression, error = wc_lang.FunctionExpression.deserialize(
f'{c.id} / {c.init_density.id}', {
wc_lang.Compartment: {
c.id: c
},
wc_lang.Parameter: {
c.init_density.id: c.init_density
},
})
assert error is None, str(error)
for i in cell.species_types.get(
__type=wc_kb.eukaryote.TranscriptSpeciesType):
model_species_type = model.species_types.create(id=i.id)
model_compartment = model.compartments.get_one(
id='m' if 'M' in i.gene.polymer.id else 'c')
model_species = model.species.get_or_create(
species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=10,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
model.distribution_init_concentrations.get_one(
id='dist-init-conc-trans5[c]').mean = 0.
complexes = {
'complex1': ('RNA Polymerase I', 'n'),
'complex2': ('RNA Polymerase II', 'n'),
'complex3': ('RNA Polymerase mitochondria', 'm'),
'complex4': ('RNA Polymerase III', 'n')
}
for k, v in complexes.items():
model_species_type = model.species_types.create(
id=k,
name=v[0],
structure=wc_lang.ChemicalStructure(
empirical_formula=EmpiricalFormula('H'),
molecular_weight=1.018,
charge=1))
model_compartment = model.compartments.get_one(id=v[1])
model_species = model.species.get_or_create(
species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=2500 if k == 'complex2' else 100,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
metabolic_participants = [
'atp', 'ctp', 'gtp', 'utp', 'ppi', 'amp', 'cmp', 'gmp', 'ump',
'h2o', 'h', 'adp', 'pi'
]
for i in metabolic_participants:
model_species_type = model.species_types.create(id=i,
name=i.upper())
for c in ['n', 'm']:
model_compartment = model.compartments.get_one(id=c)
model_species = model.species.get_or_create(
species_type=model_species_type,
compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=1500,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
for i in ['activator', 'repressor']:
model_species_type = model.species_types.create(id=i,
name=i.upper())
model_compartment = model.compartments.get_one(id='m')
model_species = model.species.get_or_create(
species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=3,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
for i in ['activator2', 'repressor2']:
model_species_type = model.species_types.create(id=i,
name=i.upper())
model_compartment = model.compartments.get_one(id='n')
model_species = model.species.get_or_create(
species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=0,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()
factors = [
'pol1_init_factor1', 'pol1_el_factor1', 'pol2_init_factor1',
'pol2_el_factor1', 'pol2_neg_factor1', 'pol3_init_factor1',
'pol3_el_factor1', 'polm_init_factor1', 'polm_el_factor1'
]
for i in factors:
model_species_type = model.species_types.create(id=i,
name=i.upper())
model_compartment = model.compartments.get_one(
id='m' if 'polm' in i else 'n')
model_species = model.species.get_or_create(
species_type=model_species_type, compartment=model_compartment)
model_species.id = model_species.gen_id()
conc_model = model.distribution_init_concentrations.create(
species=model_species,
mean=2,
units=unit_registry.parse_units('molecule'))
conc_model.id = conc_model.gen_id()